Skip to content
NewA calmer, faster ZeroHour

OpenAI says new safeguards blunt reasoning extraction on GPT-6.2

Original title: OpenAI makes it much harder for attackers to extract how its latest AI models think

The Decoderby Matthias Bastian ()1 min read
Part of a story covered by 2 sourcesOpenAI hardens GPT-6.2 against extraction of protected reasoningMerged summary & timeline
AI summary · x-ai/grok-4.7Summaries by Vani AI

Internal tests put prior-request extraction at 0.2 percent, down from 54.0 percent on GPT-6 Astra.

OpenAI said it tightened protections against extracting internal reasoning from GPT-6.2 Astra and GPT-6.2 Sol. In its automated tests, prior-request extraction fell from 54.0 percent on GPT-6 Astra to 0.2 percent, and current-request attacks from 22.9 to 0.9 percent. Defenses include training, input and output filters, API blocks, and weekly bans of thousands to tens of thousands of accounts. Selected improvements are also coming to GPT-6 Astra.

Unconfirmed: The success rates are OpenAI's own internal test figures, not independent measurements.

Key facts
  • Rates are aggregated across six attacker models in adaptive black-box tests.
  • API blocks stop older models from reading protected reasoning.
  • OpenAI bans thousands to tens of thousands of accounts weekly.
  • Anthropic also reports banning accounts over distillation of internal reasoning.
Explain this AI news with Vani AIWhat was announced, what is new and why it matters, in a new chat

From the original article

1 min read at the-decoder.com

OpenAI has significantly strengthened safeguards against extracting internal reasoning from GPT-6. 2 Astra and GPT-6. 2 Sol.

The Decoder

By Matthias Bastian · the-decoder.com

Read the full article at The Decoder

A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.